Nicholas Decker In Hell - by Scott Alexander
substack.com · 3,552 words · saved by 1 readers
...
I. Econblogger Nicholas Decker is not a fan of AI 2040: One of the centerpieces of AI 2040 is the proposal that we pause the development of AI at a high level, use the AI to research alignment, and only then proceed. I am skeptical of this, and not only because it seems impractical to get such cooperation. My first argument is that I do not believe a period of “researching alignment” is meaningful – alignment research is simply capabilities research, patching particular bugs in the system, and we’re not going to find anything deep without actually being in contact with the systems […] I…
saved by
related reading
- My AI Opinions - by Scott Alexander - Astral Codex Tensubstack.com
- The future of AI crimesubstack.com
- What failure looks like — LessWronglesswrong.com
- Deep Deceptiveness — LessWronglesswrong.com
- What failure looks like — AI Alignment Forumalignmentforum.org
- The Artificiality of Alignmentjoinreboot.org
- Current AIs seem pretty misaligned to me — LessWronglesswrong.com
- Model Organisms of Misalignment: The Case for a New Pillar of Alignment Research — AI Alignment Forumalignmentforum.org
- Why AI alignment could be hard with modern deep learningcold-takes.com
- How do we (more) safely defer to AIs? — LessWronglesswrong.com
- There Is No A.I. | The New Yorkernewyorker.com
- Self-Fulfilling Misalignment Data Might Be Poisoning Our AI Modelsturntrout.com